Konstantinos Platanitis, Miguel Arana-Catania, Leonardo Capicchiano, Saurabh Upadhyay, Leonard Felicetti
{"title":"利用时间序列聚类和强化学习估算航天器惯性参数","authors":"Konstantinos Platanitis, Miguel Arana-Catania, Leonardo Capicchiano, Saurabh Upadhyay, Leonard Felicetti","doi":"arxiv-2408.03445","DOIUrl":null,"url":null,"abstract":"This paper presents a machine learning approach to estimate the inertial\nparameters of a spacecraft in cases when those change during operations, e.g.\nmultiple deployments of payloads, unfolding of appendages and booms, propellant\nconsumption as well as during in-orbit servicing and active debris removal\noperations. The machine learning approach uses time series clustering together\nwith an optimised actuation sequence generated by reinforcement learning to\nfacilitate distinguishing among different inertial parameter sets. The\nperformance of the proposed strategy is assessed against the case of a\nmulti-satellite deployment system showing that the algorithm is resilient\ntowards common disturbances in such kinds of operations.","PeriodicalId":501163,"journal":{"name":"arXiv - PHYS - Instrumentation and Methods for Astrophysics","volume":"90 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spacecraft inertial parameters estimation using time series clustering and reinforcement learning\",\"authors\":\"Konstantinos Platanitis, Miguel Arana-Catania, Leonardo Capicchiano, Saurabh Upadhyay, Leonard Felicetti\",\"doi\":\"arxiv-2408.03445\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper presents a machine learning approach to estimate the inertial\\nparameters of a spacecraft in cases when those change during operations, e.g.\\nmultiple deployments of payloads, unfolding of appendages and booms, propellant\\nconsumption as well as during in-orbit servicing and active debris removal\\noperations. The machine learning approach uses time series clustering together\\nwith an optimised actuation sequence generated by reinforcement learning to\\nfacilitate distinguishing among different inertial parameter sets. The\\nperformance of the proposed strategy is assessed against the case of a\\nmulti-satellite deployment system showing that the algorithm is resilient\\ntowards common disturbances in such kinds of operations.\",\"PeriodicalId\":501163,\"journal\":{\"name\":\"arXiv - PHYS - Instrumentation and Methods for Astrophysics\",\"volume\":\"90 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Instrumentation and Methods for Astrophysics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2408.03445\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Instrumentation and Methods for Astrophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2408.03445","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Spacecraft inertial parameters estimation using time series clustering and reinforcement learning
This paper presents a machine learning approach to estimate the inertial
parameters of a spacecraft in cases when those change during operations, e.g.
multiple deployments of payloads, unfolding of appendages and booms, propellant
consumption as well as during in-orbit servicing and active debris removal
operations. The machine learning approach uses time series clustering together
with an optimised actuation sequence generated by reinforcement learning to
facilitate distinguishing among different inertial parameter sets. The
performance of the proposed strategy is assessed against the case of a
multi-satellite deployment system showing that the algorithm is resilient
towards common disturbances in such kinds of operations.